Open AccessClassification of Alzheimer’s disease in MobileNet
Author(s) -
Xiaoling Lü,
Haifeng Wu,
Yu Zeng
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/4/042012
Subject(s) - convolutional neural network , artificial intelligence , transfer of learning , deep learning , computer science , disease , artificial neural network , magnetic resonance imaging , machine learning , alzheimer's disease , pattern recognition (psychology) , medicine , pathology , radiology
As the aging of Chinese society becomes more and more serious, the number of elderly people has increased dramatically. At the same time, the number of patients with Alzheimer’s disease (AD) has increased. At present, the main diagnostic method for Alzheimer’s disease relies on experienced radiologists to analyse brain structural nuclear magnetic resonance (MRI) images to judge the condition, but this method is time-consuming and labor-intensive, and there is a certain subjectivity. This may cause misdiagnosis. By classifying the MRI images of patients with Alzheimer’s disease and healthy controls (NC), for image classification, the Convolutional Neural Network (CNN) in deep learning has outstanding performance and accurate classification. The VGG 16 network model and the MobileNet network model of the convolutional neural network are compared, using deep learning and transfer learning. We can find that the MobileNet network model is superior to the VGG 16 network model in classification accuracy.